© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199424
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     መስ
    0.43
     cape
    0.43
    ربعة
    0.42
     entrop
    0.40
     웹
    0.39
     布
    0.38
    લાઇ
    0.38
     Robb
    0.38
    +#+#+
    0.38
    Aless
    0.37
    POSITIVE LOGITS
     న
    0.38
     enumerate
    0.36
    тере
    0.35
    dict
    0.34
    enumeration
    0.34
     बालक
    0.34
    jokes
    0.34
     plano
    0.33
    วล
    0.33
     enumeration
    0.33
    Activations Density 0.000%

    No Known Activations